Contextual AI models for single-cell protein biology.

Understanding protein function and developing molecular therapies require deciphering the cell types in which proteins act as well as the interactions between proteins. However, modeling protein interactions across biological contexts remains challenging for existing algorithms. Here we introduce PINNACLE, a geometric deep learning approach that generates context-aware protein representations. Leveraging a multiorgan single-cell atlas, PINNACLE learns on contextualized protein interaction networks to produce 394,760 protein representations from 156 cell type contexts across 24 tissues. PINNACLE's embedding space reflects cellular and tissue organization, enabling zero-shot retrieval of the tissue hierarchy. Pretrained protein representations can be adapted for downstream tasks: enhancing 3D structure-based representations for resolving immuno-oncological protein interactions, and investigating drugs' effects across cell types. PINNACLE outperforms state-of-the-art models in nominating therapeutic targets for rheumatoid arthritis and inflammatory bowel diseases and pinpoints cell type contexts with higher predictive capability than context-free models. PINNACLE's ability to adjust its outputs on the basis of the context in which it operates paves the way for large-scale context-specific predictions in biology.

Postoperative anemia in cardiac surgery patients: a narrative review.

PURPOSE: Anemia reduces the blood's ability to carry and deliver oxygen. Following cardiac surgery, anemia is very common and affects up to 90% of patients. Nevertheless, there is a paucity of data examining the prognostic value of postoperative anemia. In this narrative review, we present findings from the relevant literature on postoperative anemia in cardiac surgery patients, focusing on the incidence, risk factors, and prognostic value of postoperative anemia. We also explore the potential utility of postoperative anemia as a therapeutic target to improve clinical outcomes. SOURCE: We conducted a targeted search of MEDLINE, Embase, and the Cochrane Database of Systematic Reviews up to September 2022, using a combination of search terms including postoperative (post-operative), perioperative (peri-operative), anemia (anaemia), and cardiac surgery. PRINCIPAL FINDINGS: The reported incidence of postoperative anemia varied from 29% to 94% across the studies, likely because of variations in patient inclusion criteria and classification of postoperative anemia. Nonetheless, the weight of the evidence suggests that postoperative anemia is common and is an independent risk factor for adverse postoperative outcomes such as acute kidney injury, stroke, mortality, and functional outcomes. CONCLUSIONS: In cardiac surgery patients, postoperative anemia is a common and prognostically important risk factor for postoperative morbidity and mortality. Nevertheless, there is a lack of data on whether active management of postoperative anemia is feasible or effective in improving patient outcomes.

RéSUMé: OBJECTIF: L'anémie réduit la capacité du sang à transporter et à fournir de l'oxygène. Suite à une chirurgie cardiaque, l'anémie est très fréquente et touche jusqu'à 90 % des patient·es. Néanmoins, il existe peu de données examinant la valeur pronostique de l'anémie postopératoire. Dans ce compte rendu narratif, nous présentons les résultats de la littérature pertinente sur l'anémie postopératoire chez les patient·es ayant bénéficié d'une chirurgie cardiaque, en mettant l'accent sur l'incidence, les facteurs de risque et la valeur pronostique de l'anémie postopératoire chez les personnes ayant bénéficié d'une chirurgie cardiaque. Nous explorons également l'utilité potentielle de l'anémie postopératoire en tant que cible thérapeutique pour améliorer les devenirs cliniques. SOURCES: Nous avons réalisé une recherche ciblée dans MEDLINE, Embase et la base de données des revues systématiques Cochrane jusqu'en septembre 2022, en utilisant une combinaison de termes de recherche, notamment postopératoire (postoperative/post-operative), périopératoire (perioperative/peri-operative), anémie (anemia/anaemia) et chirurgie cardiaque (cardiac surgery). CONSTATATIONS PRINCIPALES: L'incidence rapportée de l'anémie postopératoire variait de 29 % à 94 % d'une étude à l'autre, probablement en raison des variations dans les critères d'inclusion des patient·es et la classification de l'anémie postopératoire. Néanmoins, le poids de la preuve suggère que l'anémie postopératoire est courante et constitue un facteur de risque indépendant pour les devenirs postopératoires indésirables tels que l'insuffisance rénale aiguë, les accidents vasculaires cérébraux, la mortalité et les devenirs fonctionnels. CONCLUSION: Chez la patientèle en chirurgie cardiaque, l'anémie postopératoire est un facteur de risque commun et pronostiquement important de morbidité et de mortalité postopératoires. Néanmoins, il y a un manque de données sur la faisabilité ou l'efficacité de la prise en charge active de l'anémie postopératoire pour améliorer les devenirs des patient·es.

Microbiota dynamics in a randomized trial of gut decontamination during allogeneic hematopoietic cell transplantation.

BACKGROUNDGut decontamination (GD) can decrease the incidence and severity of acute graft-versus-host disease (aGVHD) in murine models of allogeneic hematopoietic cell transplantation (HCT). In this pilot study, we examined the impact of GD on gut microbiome composition and the incidence of aGVHD in HCT patients.METHODSWe randomized 20 patients undergoing allogeneic HCT to receive (GD) or not receive (no-GD) oral vancomycin-polymyxin B from day -5 through neutrophil engraftment. We evaluated shotgun metagenomic sequencing of serial stool samples to compare the composition and diversity of the gut microbiome between study arms. We assessed clinical outcomes in the 2 arms and performed strain-specific analyses of pathogens that caused bloodstream infections (BSI).RESULTSThe 2 arms did not differ in the predefined primary outcome of Shannon diversity of the gut microbiome at 2 weeks post-HCT (genus, P = 0.8; species, P = 0.44) or aGVHD incidence (P = 0.58). Immune reconstitution of T cell and B cell subsets was similar between groups. Five patients in the no-GD arm had 8 BSI episodes versus 1 episode in the GD arm (P = 0.09). The BSI-causing pathogens were traceable to the gut in 7 of 8 BSI episodes in the no-GD arm, including Staphylococcus species.CONCLUSIONWhile GD did not differentially affect Shannon diversity or clinical outcomes, our findings suggest that GD may protect against gut-derived BSI in HCT patients by decreasing the prevalence or abundance of gut pathogens.TRIAL REGISTRATIONClinicalTrials.gov NCT02641236.FUNDINGNIH, Damon Runyon Cancer Research Foundation, V Foundation, Sloan Foundation, Emerson Collective, and Stanford Maternal & Child Health Research Institute.